© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63585
    Prev
    Next
    INDEX
    Explanations

    special characters and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ates
    -0.07
    earing
    -0.07
    ä¸Ĭè¿°
    -0.07
    鸦
    -0.06
    ata
    -0.06
    uss
    -0.06
     Lauf
    -0.06
    对ä¸Ĭè¿°
    -0.06
    æĹ¥ä¸Ĭ
    -0.06
    aign
    -0.06
    POSITIVE LOGITS
    æ¯Ķèĩªå·±
    0.08
    èĪĩåħ¶
    0.08
    æīĢåѦä¸ĵä¸ļ
    0.08
    æĪĸä¸İ
    0.08
    æ¯Ķä»ĸ
    0.07
    ä¸İä¹ĭ
    0.07
    çĻ¾éĩĮ
    0.07
    į¨
    0.07
    ulet
    0.07
    ä¸İåħ¶
    0.07
    Activations Density 0.121%

    No Known Activations